{"id":"https://openalex.org/W7133229839","doi":"https://doi.org/10.48550/arxiv.2602.23630","title":"BTTackler: A Diagnosis-based Framework for Efficient Deep Learning Hyperparameter Optimization","display_name":"BTTackler: A Diagnosis-based Framework for Efficient Deep Learning Hyperparameter Optimization","publication_year":2026,"publication_date":"2026-02-27","ids":{"openalex":"https://openalex.org/W7133229839","doi":"https://doi.org/10.48550/arxiv.2602.23630"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2602.23630","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2602.23630","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2602.23630","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5063244527","display_name":"Zhongyi Pei","orcid":"https://orcid.org/0000-0002-4324-6989"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Pei, Zhongyi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005157168","display_name":"Zhiyao Cen","orcid":"https://orcid.org/0009-0001-8836-6773"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Cen, Zhiyao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5127859936","display_name":"Yipeng Huang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Huang, Yipeng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5127807889","display_name":"Chen Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Chen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5127813251","display_name":"Lin Liu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liu, Lin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5127860016","display_name":"Philip S Yu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yu, Philip","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5127804064","display_name":"Mingsheng Long","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Long, Mingsheng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12535","display_name":"Machine Learning and Data Classification","score":0.9850000143051147,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T12535","display_name":"Machine Learning and Data Classification","score":0.9850000143051147,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11948","display_name":"Machine Learning in Materials Science","score":0.0024999999441206455,"subfield":{"id":"https://openalex.org/subfields/2505","display_name":"Materials Chemistry"},"field":{"id":"https://openalex.org/fields/25","display_name":"Materials Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10848","display_name":"Advanced Multi-Objective Optimization Algorithms","score":0.0020000000949949026,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/hyperparameter","display_name":"Hyperparameter","score":0.9013000130653381},{"id":"https://openalex.org/keywords/baseline","display_name":"Baseline (sea)","score":0.5285999774932861},{"id":"https://openalex.org/keywords/hyperparameter-optimization","display_name":"Hyperparameter optimization","score":0.527999997138977},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.524399995803833},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.4636000096797943},{"id":"https://openalex.org/keywords/python","display_name":"Python (programming language)","score":0.43309998512268066},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.43149998784065247}],"concepts":[{"id":"https://openalex.org/C8642999","wikidata":"https://www.wikidata.org/wiki/Q4171168","display_name":"Hyperparameter","level":2,"score":0.9013000130653381},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7577000260353088},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.7069000005722046},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6712999939918518},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.5285999774932861},{"id":"https://openalex.org/C10485038","wikidata":"https://www.wikidata.org/wiki/Q48996162","display_name":"Hyperparameter optimization","level":3,"score":0.527999997138977},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.524399995803833},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4636000096797943},{"id":"https://openalex.org/C519991488","wikidata":"https://www.wikidata.org/wiki/Q28865","display_name":"Python (programming language)","level":2,"score":0.43309998512268066},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.43149998784065247},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.39100000262260437},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.38269999623298645},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.3546000123023987},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.33410000801086426},{"id":"https://openalex.org/C13662910","wikidata":"https://www.wikidata.org/wiki/Q193139","display_name":"Trajectory","level":2,"score":0.31119999289512634},{"id":"https://openalex.org/C534262118","wikidata":"https://www.wikidata.org/wiki/Q177719","display_name":"Medical diagnosis","level":2,"score":0.29269999265670776},{"id":"https://openalex.org/C147764199","wikidata":"https://www.wikidata.org/wiki/Q6865248","display_name":"Minification","level":2,"score":0.25760000944137573}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2602.23630","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2602.23630","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2602.23630","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2602.23630","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Hyperparameter":[0],"optimization":[1,84],"(HPO)":[2],"is":[3],"known":[4],"to":[5,30,81,124,214,220,253,257],"be":[6,61],"costly":[7],"in":[8,66,76],"deep":[9,168],"learning,":[10],"especially":[11],"when":[12],"leveraging":[13],"automated":[14,20,185,258],"approaches.":[15],"Most":[16],"of":[17,34,70,98,142,165,183,203,211],"the":[18,32,67,71,87,96,181,201,216],"existing":[19],"HPO":[21,118,162,176,186,259],"methods":[22,222,235],"are":[23,28,155,158],"accuracy-based,":[24],"i.e.,":[25],"accuracy":[26,64,195,218],"metrics":[27,65],"used":[29,175],"guide":[31],"trials":[33,45,89,232],"different":[35],"hyperparameter":[36,101],"configurations":[37,102],"amongst":[38],"a":[39,104,116,140,239],"specific":[40],"search":[41],"space.":[42],"However,":[43],"many":[44],"may":[46],"encounter":[47],"severe":[48],"training":[49,72,122,126,153],"problems,":[50],"such":[51],"as":[52],"vanishing":[53],"gradients":[54],"and":[55,73,94,129,147,172,196,225],"insufficient":[56],"convergence,":[57],"which":[58],"can":[59],"hardly":[60],"reflected":[62],"by":[63,138],"early":[68,149],"stages":[69],"often":[74],"result":[75],"poor":[77],"performance.":[78],"This":[79],"leads":[80],"an":[82,184,246],"inefficient":[83],"trajectory":[85],"because":[86],"bad":[88,132],"occupy":[90],"considerable":[91],"computation":[92],"resources":[93],"reduce":[95],"probability":[97],"finding":[99],"excellent":[100],"within":[103,238],"time":[105,197,212,241],"limitation.":[106],"In":[107],"this":[108],"paper,":[109],"we":[110,188],"propose":[111,189],"\\textbf{Bad":[112],"Trial":[113],"Tackler":[114],"(BTTackler)},":[115],"novel":[117],"framework":[119],"that":[120,250],"introduces":[121],"diagnosis":[123],"identify":[125],"problems":[127,154],"automatically":[128],"hence":[130],"tackles":[131],"trials.":[133],"BTTackler":[134,204,256],"diagnoses":[135],"each":[136],"trial":[137],"calculating":[139],"set":[141],"carefully":[143],"designed":[144],"quantified":[145],"indicators":[146],"triggers":[148],"termination":[150],"if":[151],"any":[152],"detected.":[156],"Evaluations":[157],"performed":[159],"on":[160,194,205,223,236],"representative":[161],"tasks":[163],"consisting":[164],"three":[166],"classical":[167],"neural":[169],"networks":[170],"(DNN)":[171],"four":[173],"widely":[174],"methods.":[177],"To":[178],"better":[179],"quantify":[180],"effectiveness":[182],"method,":[187],"two":[190],"new":[191],"measurements":[192],"based":[193],"consumption.":[198],"Results":[199],"show":[200],"advantage":[202],"two-fold:":[206],"(1)":[207],"it":[208,227],"reduces":[209],"40.33\\%":[210],"consumption":[213],"achieve":[215],"same":[217],"comparable":[219],"baseline":[221,234],"average":[224,237],"(2)":[226],"conducts":[228],"44.5\\%":[229],"more":[230],"top-10":[231],"than":[233],"given":[240],"budget.":[242],"We":[243],"also":[244],"released":[245],"open-source":[247],"Python":[248],"library":[249],"allows":[251],"users":[252],"easily":[254],"apply":[255],"processes":[260],"with":[261],"minimal":[262],"code":[263],"changes.":[264]},"counts_by_year":[],"updated_date":"2026-07-28T07:46:37.118299","created_date":"2026-03-03T00:00:00"}